Charbonnier Loss (L1)

r""" Image to Patch Embedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

r""" Image to Patch Unembedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

# ----------------------------------------- # Get L/H for denosing on AWGN with fixed sigma. # Only dataroot_H is needed. # ---------

# ----------------------------------------- # Get L/H for denosing on AWGN with fixed sigma. # Only dataroot_H is needed. # ---------

@inproceedings{hui2019lightweight, title={Lightweight Image Super-Resolution with Information Multi-distillation Network}, author={Hu

Train with pixel loss

VGG Perceptual loss

r"""Rearranges elements in a Tensor of shape :math:`(C, rH, rW)` to a tensor of shape :math:`(*, r^2C, H, W)`. Authors: Zhaoyi Yan, h

Upsample module. Args: scale (int): Scale factor. Supported scales: 2^n and 3. num_feat (int): Channel number of intermediate fea

UpsampleOneStep module (the difference with Upsample is that it always only has 1conv + 1pixelshuffle) Used in lightweight SR to save parameter